Abstract
One of the challenging topics in the field of computer vision is the detection of the stationary/non-stationary objects from a video sequence. The outcome of detection, tracking, and learning must be free from ambiguity. For effectively detecting the moving object, first the background information from the video should be subtracted. However, in the high-definition video, modeling techniques suffer from high computation and memory cost which may lead to a decrease in performance measure such as accuracy and efficiency in identifying the object accurately. It is important to identify the definite structure from a large amount of unstructured data which is a prerequisite problem to be solved. The task of finding the structure from a large amount of data is achieved using Deep Learning ‘which is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text’. The purpose of the paper is to survey the method with which the objects can be efficiently detected from any given video sequence along with the preferable use of the deep learning library.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Machine Learning.: http://www.mlplatform.nl/what-is-machine-learning. Accessed 01 Jan 2016
Mitchell, T.M.: Machine Learning, p. 421. McGraw-Hill Science/Engineering/Math (1997)
Deng, L., Yu, D.: Deep learning methods and applications. Found. Trends Sign. Process. 7(3–4), 197–387 (2014) [Now Publishers Inc. Hanover, MA, USA]
Jang, H., Yang, H.-J., Jeong, D.-S.: Object classification using CNN for video traffic detection system. In: 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV), pp. 1–4. IEEE (2015)
Collaborative Filtering.: http://benanne.github.io/2014/08/05/spotify-cnns.html. Accessed 20 Sept 2016
Le, Q.V., Ngiam, J., Coates, A., Lahiri, A., Prochnow, B., Ng, A.Y.: On optimization methods for deep learning. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), Bellevue, WA, USA, pp. 265–272 (2011)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell., Elsevier, North Holland 17, 185–203 (1981) [Technical Report, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, USA (1980)]
Dosovitskiy, A., Fischer, P., Ilg, E., Häusser, P., Hazırbaş, C., Golkov, V., Smagt, P., Cremers, D., Brox, T.: Flownet: learning optical flow with convolutional networks. In: IEEE International Conference on Computer Vision (ICCV 2015), Santiago, Chile (2015)
Flying Chairs Dataset.: http://lmb.informatik.unifreiburg.de/resources/datasets/FlyingChairs.en.html. Accessed 19 Sept 2016
Feature Detection and Extraction.: http://in.mathworks.com/help/vision/feature-detection-andextraction.html. Accessed 14 July 2016
Nguyen, K., Fookes, C., Sridharan, S.: Improving deep convolutional neural networks with unsupervised feature learning. In: International Conference on Image Processing (ICIP 2015), pp. 2270–2274. IEEE (2015)
Chen, Y., Yang, X., Zhong, B., Pan, S., Chen, D., Zhang, H.: CNNTracker: online discriminative object tracking via deep convolutional neural network. Appl. Soft Comput. 38, 1088–1098 (2015) [Elsevier]
Ouyang, W., Wang, X.: Joint deep learning for pedestrian detection, computer vision foundation. In: Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV’13), pp. 2056–2063. IEEE Computer Society, Washington, DC, USA (2013)
Zhang, Y., Li, X., Zhang, Z., Wu, F., Zhao, L.: Deep learning driven blockwise moving object detection with binary scene modeling. Neurocomputing 168, 454–463 (2015) [Elsevier]. http://arxiv.org/abs/1601.07265
LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’04), pp. 97–104. IEEE Computer Society, Washington, DC, USA (2004)
Jin, L., Gao, S.: Hand-crafted features or machine learnt features? Together they improve RGB-D object recognition. In: Proceedings of the 2014 IEEE International Symposium on Multimedia (ISM’14), pp. 311–319. IEEE Computer Society, Washington, DC, USA (2014)
Caffe.: http://caffe.berkeleyvision.org. Accessed 30 Mar 2016
Deep Learning Frameworks.: https://github.com/zer0n/deepframeworks#architecture. Accessed 28 Mar 2016
Deep Learning Libraries.: http://machinelearningmastery.com/popular-deep-learning-libraries. Accessed 28 Mar 2016
Applications.: https://www.quora.com/What-are-the-practical-applications-of-deep-learning-What-are-all-the-major-areas-fields. Accessed 18 Feb 2016
Cascade.: http://www.svcl.ucsd.edu/projects/Cascades. Accessed 10 June 2016
Convnet.: http://fastml.com/object-recognition-in-images-with-cuda-convnet. Accessed 28 July 2016
Optical Flow.: http://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-34-video-analytics-lasalle-2016. Accessed 19 Sept 2016
Background Subtraction.: http://www.slideshare.net/ravi5raj_88/background-subtraction. Accessed 04 Aug 2016
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Garg, D., Kotecha, K. (2018). Object Detection from Video Sequences Using Deep Learning: An Overview. In: Choudhary, R., Mandal, J., Bhattacharyya, D. (eds) Advanced Computing and Communication Technologies. Advances in Intelligent Systems and Computing, vol 562. Springer, Singapore. https://doi.org/10.1007/978-981-10-4603-2_14
Download citation
DOI: https://doi.org/10.1007/978-981-10-4603-2_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-4602-5
Online ISBN: 978-981-10-4603-2
eBook Packages: EngineeringEngineering (R0)